[PATCH] D134568: [AMDGPU] Add pattern for flat fadd f64 intrinsic with local address

[Petar Avramovic via Phabricator via llvm-commits]

Petar.Avramovic created this revision.
Petar.Avramovic added reviewers: arsenm, foad.
Herald added subscribers: kosarev, kerbowa, hiraditya, t-tye, Anastasia, tpr, dstuttard, yaxunl, jvesely, kzhuravl.
Herald added a project: All.
Petar.Avramovic requested review of this revision.
Herald added subscribers: llvm-commits, wdng.
Herald added a project: LLVM.

Fixes regression from clang opencl test in test_flat_add_local_f64
file /clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx90a.cl, caused by D130579 <https://reviews.llvm.org/D130579>.
Looks fine for f64, I am not sure how it should work for f32.
Will look in detail later.


https://reviews.llvm.org/D134568

Files:
  clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx90a.cl
  llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
  llvm/lib/Target/AMDGPU/DSInstructions.td
  llvm/test/CodeGen/AMDGPU/fp64-atomics-gfx90a.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D134568.462593.patch
Type: text/x-patch
Size: 5372 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220923/f5b991b0/attachment.bin>